Ensemble Models for dependency parsing: Cheap and good?

Mihai Surdeanu, Christopher D. Manning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

61 Scopus citations

Abstract

Previous work on dependency parsing used various kinds of combination models but a systematic analysis and comparison of these approaches is lacking. In this paper we implemented such a study for English dependency parsing and find several non-obvious facts: (a) the diversity of base parsers is more important than complex models for learning (e.g., stacking, supervised meta-classification), (b) approximate, linear-time re-parsing algorithms guarantee well-formed dependency trees without significant performance loss, and (c) the simplest scoring model for re-parsing (unweighted voting) performs essentially as well as other more complex models. This study proves that fast and accurate ensemble parsers can be built with minimal effort.

Original languageEnglish (US)
Title of host publicationNAACL HLT 2010 - Human Language Technologies
Subtitle of host publicationThe 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference
Pages649-652
Number of pages4
StatePublished - 2010
Externally publishedYes
Event2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010 - Los Angeles, CA, United States
Duration: Jun 2 2010Jun 4 2010

Publication series

NameNAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference

Other

Other2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010
Country/TerritoryUnited States
CityLos Angeles, CA
Period6/2/106/4/10

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Ensemble Models for dependency parsing: Cheap and good?'. Together they form a unique fingerprint.

Cite this